Mask Estimation For Missing Data Recognition Using Background Noise Sniffing

Sébastien Demange 1 Christophe Cerisara 1 Jean-Paul Haton 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper addresses the problem of spectrographic mask estimation in the context of missing data recognition. At the difference of other denoising methods, missing data recognition does not match the whole spectrum with the acoustic models, but rather considers that some time-frequency pixels are missing, i.e. corrupted by noise. Correctly estimating these ``masks'' is very important for missing data recognizers. We propose a new approach that exploits some a priori knowledge about these masks in typical noisy environments to address this difficult challenge. The proposed mask is then obtained by combining these noise dependent masks. The combination is led by an environmental ``sniffing'' module that estimates the probability of being in each typical noisy condition. This missing data mask estimation procedure has been integrated in a complete missing data recognizer using bounded marginalization. Our approach is evaluated on the Aurora2 database.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2006, May 2006, Toulouse/France, 2006
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00080562
Contributeur : Sébastien Demange <>
Soumis le : lundi 19 juin 2006 - 15:05:09
Dernière modification le : jeudi 11 janvier 2018 - 06:19:56
Document(s) archivé(s) le : lundi 5 avril 2010 - 23:03:01

Fichiers

Identifiants

  • HAL Id : inria-00080562, version 1

Collections

Citation

Sébastien Demange, Christophe Cerisara, Jean-Paul Haton. Mask Estimation For Missing Data Recognition Using Background Noise Sniffing. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2006, May 2006, Toulouse/France, 2006. 〈inria-00080562〉

Partager

Métriques

Consultations de la notice

265

Téléchargements de fichiers

377